提出快速修复暗光3D场景的图像增强与去模糊方法
Fast Low-light Enhancement and Deblurring for 3D Dark Scenes
- 将3D场景恢复设计为增强与重建交替循环
- 训练快21倍，渲染快11倍，有效抑制噪声放大
- 适合需要实时处理低光模糊3D影像的科研与应用
从低光、噪声大且运动模糊的图像中进行新视角合成仍是一项重要而困难的任务。现有体素渲染方法难以应对多重退化，而传统的2D顺序预处理会因依赖关系引入伪影。本文提出FLED-GS框架，将3D场景恢复重构为增强与重建的交替循环。具体地，通过插入多个中间亮度锚点实现渐进式恢复，防止噪声放大影响去模糊或几何重建。每次迭代使用现成的2D去模糊器锐化输入，并执行感知噪声的3DGS重建，估计并抑制噪声，同时生成下一阶段的干净先验。实验表明，FLED-GS优于当前最优方法LuSh-NeRF，实现21倍更快的训练速度和11倍更快的渲染速度。
原文摘要 · Abstract (English)
Novel view synthesis from low-light, noisy, and motion-blurred imagery remains a valuable and challenging task. Current volumetric rendering methods struggle with compound degradation, and sequential 2D preprocessing introduces artifacts due to interdependencies. In this work, we introduce FLED-GS, a fast low-light enhancement and deblurring framework that reformulates 3D scene restoration as an alternating cycle of enhancement and reconstruction. Specifically, FLED-GS inserts several intermediate brightness anchors to enable progressive recovery, preventing noise blow-up from harming deblurring or geometry. Each iteration sharpens inputs with an off-the-shelf 2D deblurrer and then performs noise-aware 3DGS reconstruction that estimates and suppresses noise while producing clean priors for the next level. Experiments show FLED-GS outperforms state-of-the-art LuSh-NeRF, achieving 21$\times$ faster training and 11$\times$ faster rendering.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。